Skip to Main content Skip to Navigation
Other publications

The LEAR submission at Thumos 2014

Dan Oneata 1 Jakob Verbeek 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : We describe the submission of the INRIA LEAR team to the THU-MOS workshop in conjunction with ECCV 2014. Our system is based on Fisher vector (FV) encoding of dense trajectory features (DTF), which we also used in our 2013 submission. This year's submission additionally incorporates static-image features (SIFT, Color, and CNN) and audio features (ASR and MFCC) for the classification task. For the detection task, we combine scores from the clas-sification task with FV-DTF features extracted from video slices. We found that these additional visual and audio feature significantly improve the classification results. For localization we found that using the classification scores as a contex-tual feature besides local motion features leads to significant improvements.
Document type :
Other publications
Complete list of metadata

Cited literature [9 references]  Display  Hide  Download
Contributor : Thoth Team Connect in order to contact the contributor
Submitted on : Monday, November 3, 2014 - 10:55:33 AM
Last modification on : Thursday, January 20, 2022 - 5:28:03 PM
Long-term archiving on: : Wednesday, February 4, 2015 - 10:05:39 AM


Files produced by the author(s)


  • HAL Id : hal-01074442, version 1



Dan Oneata, Jakob Verbeek, Cordelia Schmid. The LEAR submission at Thumos 2014. 2014. ⟨hal-01074442⟩



Les métriques sont temporairement indisponibles